Research map / Video / Video segmentation and tracking
MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement
Wenbo Bao, Wei‐Sheng Lai, Xiaoyun Zhang, Zhiyong Gao, Ming–Hsuan Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add mask estimation to flow-based model (ablation) | MEMC-Net (bilinear kernel, no post-proc) · Vimeo90K | PSNR: 32.73 -> 32.94 | Improved |
| add post-processing network to flow-based model (ablation) | MEMC-Net (bilinear kernel, no mask) · Vimeo90K | PSNR: 32.73 -> 33.25 | Improved |
| add both mask estimation and post-processing (ablation) | MEMC-Net (bilinear kernel) · Vimeo90K | PSNR: 32.73 -> 33.40 | Improved |
| replace fixed bilinear kernel with learned adaptive kernel (ablation) | MEMC-Net (mask and post-proc) · Vimeo90K | PSNR: 33.40 -> 34.02 | Improved |
| replace bilinear kernel with learned kernel without mask (ablation) | MEMC-Net (post-proc, no mask) · Vimeo90K | PSNR: 33.25 -> 33.29 | No clear effect |
| fine-tune the flow estimation network instead of fixing it (ablation) | MEMC-Net · Vimeo90K | PSNR: 32.05 -> 34.02 | Improved |
| add flow estimation network to kernel-only model (ablation) | MEMC-Net (kernel only, post-proc) · Vimeo90K | PSNR: 33.31 -> 34.02 | Improved |
| add flow estimation network to kernel-only model (ablation) | MEMC-Net (kernel only, post-proc) · UCF101 | PSNR: 34.97 -> 34.95 | No clear effect |
| use parallel flow and kernel estimation instead of sequential model (ablation) | MEMC-Net · Vimeo90K | PSNR: 32.94 -> 34.02 | Improved |
| use full model instead of small SPyNet-based model (ablation) | MEMC-Net_s to MEMC-Net · Middlebury Other set | interpolation error: 2.44 -> 2.24 | Mixed |
| add context information and residual blocks | MEMC-Net to MEMC-Net* · Vimeo90K | PSNR: 34.02 -> 34.40 | Improved |
| use multi-frame MEMC-Net_DN instead of single-frame EDSR_DN | video denoising · Vimeo90K | PSNR: 35.11 -> 36.35 | Improved |
Later papers that compared with this method
5 later accepted papers report MEMC-Net* as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.
- Multiple Video Frame Interpolation via Enhanced Deformable Separable Convolution (TPAMI 2021 · better on 1 of 1 shared result)
- A Flexible Recurrent Residual Pyramid Network for Video Frame Interpolation (ECCV 2020 · better on 6 of 6 shared results)
- BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation (ECCV 2020 · better on 4 of 4 shared results)
- Video Frame Interpolation via Deformable Separable Convolution (AAAI 2020 · better on 3 of 3 shared results)
- Depth-Aware Video Frame Interpolation (CVPR 2019 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- IM-Net for High Resolution Video Frame Interpolation (CVPR 2019 · similarity 0.89)
- Video Frame Interpolation via Adaptive Convolution (CVPR 2017 · similarity 0.87)
- Channel Attention Is All You Need for Video Frame Interpolation (AAAI 2020 · similarity 0.86)
- Video Frame Interpolation via Adaptive Separable Convolution (ICCV 2017 · similarity 0.86)
- Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation (CVPR 2018 · similarity 0.86)
- Disentangled Motion Modeling for Video Frame Interpolation (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
